CV-attention机制

1. SENet

源自论文《Squeeze-and-Excitation Networks》

class SELayer(nn.Module):
    def __init__(self, channel, reduction=16):
        super(SELayer, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction, bias=False),
            nn.ReLU(inplace=True),
            nn.Linear(channel // reduction, channel, bias=False),
            nn.Sigmoid()
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y.expand_as(x)

2.SKNet

源自论文《Selective Kernel Networks》

class SKLayer(nn.Module):
    def __init__(self, features, WH, M, G, r, stride=1, L=32):
        super(SKLayer, self).__init__()
        d = max(int(features / r), L)
        self.M = M
        self.features = features
        self.convs = nn.ModuleList([])
        for i in range(M):
            # 使用不同kernel size的卷积
            self.convs.append(
                nn.Sequential(
                    nn.Conv2d(features,
                              features,
                              kernel_size=3 + i * 2,
                              stride=stride,
                              padding=1 + i,
                              groups=G), 
                              nn.BatchNorm2d(features), 
                              nn.ReLU(inplace=False))
                              )
            
        self.fc = nn.Linear(features, d)
        self.fcs = nn.ModuleList([])
        for i in range(M):
            self.fcs.append(nn.Linear(d, features))
        self.softmax = nn.Softmax(dim=1)

    def forward(self, x):
        for i, conv in enumerate(self.convs):
            fea = conv(x).unsqueeze_(dim=1)
            if i == 0:
                feas = fea
            else:
                feas = torch.cat([feas, fea], dim=1)
        fea_U = torch.sum(feas, dim=1)
        fea_s = fea_U.mean(-1).mean(-1)
        fea_z = self.fc(fea_s)
        for i, fc in enumerate(self.fcs):
            print(i, fea_z.shape)
            vector = fc(fea_z).unsqueeze_(dim=1)
            print(i, vector.shape)
            if i == 0:
                attention_vectors = vector
            else:
                attention_vectors = torch.cat([attention_vectors, vector],dim=1)
        attention_vectors = self.softmax(attention_vectors)
        attention_vectors = attention_vectors.unsqueeze(-1).unsqueeze(-1)
        fea_v = (feas * attention_vectors).sum(dim=1)
        return fea_v

3.CBAM模块

源自论文《CBAM: Convolutional Block Attention Module》

class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)

        self.sharedMLP = nn.Sequential(
            nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False), nn.ReLU(),
            nn.Conv2d(in_planes // ratio, in_planes, 1, bias=False))
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        avgout = self.sharedMLP(self.avg_pool(x))
        maxout = self.sharedMLP(self.max_pool(x))
        return self.sigmoid(avgout + maxout)

class SpatialAttention(nn.Module):
    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()
        assert kernel_size in (3,7), "kernel size must be 3 or 7"
        padding = 3 if kernel_size == 7 else 1

        self.conv = nn.Conv2d(2,1,kernel_size, padding=padding, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        avgout = torch.mean(x, dim=1, keepdim=True)
        maxout, _ = torch.max(x, dim=1, keepdim=True)
        x = torch.cat([avgout, maxout], dim=1)
        x = self.conv(x)
        return self.sigmoid(x)


class BasicBlock(nn.Module):
    expansion = 1
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.ca = ChannelAttention(planes)
        self.sa = SpatialAttention()
        self.downsample = downsample
        self.stride = stride
    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        out = self.ca(out) * out  # 广播机制
        out = self.sa(out) * out  # 广播机制
        if self.downsample is not None:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out
        

4. scSE模块

源自论文《Concurrent Spatial and Channel ‘Squeeze & Excitation’ in Fully Convolutional Networks》
针对（医学图像）分割问题

class sSELayer(nn.Module):
    def __init__(self, in_channels):
        super(sSELayer, self).__init__()
        self.Conv = nn.Conv2d(in_channels, 1, kernel_size=1, bias=False)
        self.Sigmoid = nn.Sigmoid()

    def forward(self, U):
        q = self.Conv(U) 
        q = self.Sigmoid(q) #[bs, 1 ,h ,w]
        return U * q 

class cSELayer(nn.Module):
    def __init__(self, in_channels):
        super(cSELayer, self).__init__()
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.Conv_Squeeze = nn.Conv2d(in_channels, in_channels // 2, kernel_size=1, bias=False)
        self.Conv_Excitation = nn.Conv2d(in_channels//2, in_channels, kernel_size=1, bias=False)
        self.Sigmoid = nn.Sigmoid()

    def forward(self, U):
        z = self.avgpool(U)# [bs, c, 1, 1]
        z = self.Conv_Squeeze(z) #[bs, c/2, 1, 1]
        z = self.Conv_Excitation(z) #[bs, c, 1, 1]
        z = self.Sigmoid(z)
        return U * z.expand_as(U)

class scSELayer(nn.Module):
    def __init__(self, in_channels):
        super(scSELayer, self).__init__()
        self.cSE = cSELayer(in_channels)
        self.sSE = sSELayer(in_channels)

    def forward(self, U):
        U_sse = self.sSE(U)
        U_cse = self.cSE(U)
        return U_cse+U_sse

5. Non-Local 模块

源自论文《Non-local Neural Networks》

6. GCNet

源自论文《GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond》

7. DANet

8. CCNet

源自论文《CCNet: Criss-Cross Attention for Semantic Segmentation》

9. Gated Fully Fusion

源自论文《Gated Fully Fusion for Semantic Segmentation》